用于时序动作检测的边界离散化与可靠分类网络
Boundary Discretization and Reliable Classification Network for Temporal Action Detection
AI总结：
针对时序动作检测中混合框架的锚点设计局限和假阳性问题，提出BDRC-Net，通过边界离散化模块融合锚点与无锚点方法，并利用可靠分类模块降低误检，在多个基准上取得竞争性性能。
摘要：
时序动作检测旨在识别动作类别，并确定未剪辑视频中每个动作实例的起止时间。混合方法通过无缝融合基于锚点和无锚点的方法，已取得显著性能。然而，混合框架中仍存在两个关键问题：（1）暴力融合和手工设计的锚点阻碍了混合方法的巨大潜力和实用性。（2）类别内预测中存在大量假阳性。本文提出了一种新颖的边界离散化与可靠分类网络（BDRC-Net），通过引入边界离散化和可靠分类模块来解决上述问题。具体而言，边界离散化模块（BDM）以边界离散化的形式优雅地融合了基于锚点和无锚点的方法，无需传统的手工锚点设计。此外，可靠分类模块（RCM）预测可靠的全局动作类别以减少假阳性。在不同基准上开展的大量实验表明，我们提出的方法取得了具有竞争力的检测性能。代码将发布于 https://github.com/zhenyingfang/BDRC-Net。
英文摘要：
Temporal action detection aims to recognize the action category and determine each action instance's starting and ending time in untrimmed videos. The mixed methods have achieved remarkable performance by seamlessly merging anchor-based and anchor-free approaches. Nonetheless, there are still two crucial issues within the mixed framework: (1) Brute-force merging and handcrafted anchor design hinder the substantial potential and practicality of the mixed methods. (2) Within-category predictions show a significant abundance of false positives. In this paper, we propose a novel Boundary Discretization and Reliable Classification Network (BDRC-Net) that addresses the issues above by introducing boundary discretization and reliable classification modules. Specifically, the boundary discretization module (BDM) elegantly merges anchor-based and anchor-free approaches in the form of boundary discretization, eliminating the need for the traditional handcrafted anchor design. Furthermore, the reliable classification module (RCM) predicts reliable global action categories to reduce false positives. Extensive experiments conducted on different benchmarks demonstrate that our proposed method achieves competitive detection performance. The code will be released at https://github.com/zhenyingfang/BDRC-Net.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
